Platform Engineer
General Compute · New York, NY · San Francisco, CA
Build the inference cloud itself: the control plane, API and serving layer that turn racks of heterogeneous GPU and ASIC hardware into a sellable product. You will define how a mixed-hardware inference fleet is scheduled, routed and served reliably, as an early hire partnering with data center and model bring-up teams.
What you'll do
- Build and own the control plane for routing, model placement and scheduling
- Build the API and serving layer exposing rack capacity as a product
- Build in reliability and observability from day one
- Scale the platform ahead of demand
- Partner with data center deployment and model bring-up teams
Requirements
- Strong systems engineering background on distributed cloud control planes and multi-tenant orchestration at scale
- Comfort being a high-impact IC rather than a manager
- Track record building reliability from scratch
- Experience with resource scheduling or bin-packing algorithms for heterogeneous compute pools
- Experience with multi-cluster federation or distributed consensus systems (Raft, ZooKeeper, or similar)
- Comfort with hardware heterogeneity and ambiguity
- Genuine interest in being an early hire at a ~6-7 person company
Nice to have
- Experience with distributed job schedulers or cluster orchestration systems (Kubernetes, Nomad, Slurm, or similar)
- Experience running non-NVIDIA accelerators (TPUs/ASICs) in production
Skills
Outlined skills are listed as required.
Full original description
About us
General Compute is the neocloud for alternative chips.
Inference is fragmenting: purpose-built silicon from SambaNova, Cerebras, Positron, d-Matrix, and others already beats GPUs on decode, and we productionize that hardware — we buy the racks, find the data center space, and run it for our customers. Each piece of hardware runs the workload it's actually built for: prefill stays on GPUs, decode moves to the chip built for it, and today that means generating tokens 5–7× faster than existing GPU-based competitors. Our customers are frontier labs, fast-growing AI application companies, and asset-light clouds.
We closed a $15M seed round in May 2026, and have since closed a $400M debt facility — $100M funded upfront by Upper90, with the balance available for drawdown — collateralized by our inference chips.
About the role
You will build the inference cloud itself — the control plane, API, and serving layer that turn racks into a sellable product. There's no existing platform team to inherit or manage, no legacy system to work around, and no established playbook to follow — just the platform itself to build, with reliability treated as core infrastructure from day one rather than something bolted on after the first outage.The technical problem is also genuinely unsolved elsewhere. The fleet is heterogeneous by design — GPUs for prefill, multiple ASIC vendors for decode — so there's no single-vendor playbook to lean on; you'll be defining how a mixed-hardware inference cloud gets scheduled, routed, and served reliably, in close partnership with the teams standing up the physical fleet.
What you'll do:
Build/own the control plane — routing, model placement, scheduling across a mixed ASIC/GPU pool
Build the API and serving layer exposing rack capacity as a sellable product
Build in reliability and observability from day one
Scale the platform ahead of the demand curve
Partner closely with data center deployment and model bring-up teams
Be a founding technical voice on platform architecture
Work at the boundary with the inference team. Own fleet-wide routing, placement, and capacity; hand off to the Inference Engineer for per-model serving performance (batching, KV-cache, quantization) rather than owning that layer yourself
What we need from you:
Strong systems engineering background on distributed cloud control planes and multi-tenant orchestration at scale (e.g., Kubernetes-style schedulers)
Comfort being a high-impact IC rather than a manager
Track record building reliability from scratch
Experience with resource scheduling or bin-packing algorithms for heterogeneous compute pools
Experience with multi-cluster federation or distributed consensus systems (Raft, ZooKeeper, or similar)
Comfort with hardware heterogeneity/ambiguity
Genuine interest in being an early hire at a ~6–7 person company
Nice-to-haves:
Experience with distributed job schedulers or cluster orchestration systems (Kubernetes, Nomad, Slurm, or similar)
Experience running non-NVIDIA accelerators (TPUs/ASICs) in production